Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical documentation and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ายเป็น
    0.36
    ρας
    0.35
    executed
    0.35
    Dot
    0.34
     зай
    0.34
    ekyll
    0.34
    successor
    0.34
     لندن
    0.34
    ankar
    0.33
    Mais
    0.33
    POSITIVE LOGITS
     convolutions
    0.43
     ImageView
    0.38
     elimina
    0.37
    inventory
    0.37
     regioni
    0.36
    TypeOf
    0.36
     sheaves
    0.36
     retom
    0.36
     şu
    0.35
     COLLE
    0.35
    Act Density 0.000%

    No Known Activations